---
title: "Navigating the Infinite Dynamic Web Space: Effective In-Context"
description: "The authors propose HintNavigator, a multi-agent framework inspired by the ACT-R theory of human cognition. 40 references."
authors: ["Guozhao Mo", "Yanjiang Liu", "Yafei Shi", "Jiawei Chen", "Yang Li", "Yaojie Lu", "Hongyu Lin", "Ben He", "Le Sun", "Bo Zheng", "Xianpei Han"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.384/"
doi: "10.18653/v1/2026.eacl-long.384"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/mo-2026-navigating-infinite-dynamic-web-space/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/mo-2026-navigating-infinite-dynamic-web-space/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/) / Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration

# Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration

**Authors:** [Guozhao Mo](https://md.research.elamur.ai/free/en/authors/guozhao-mo/), Yanjiang Liu, [Yafei Shi](https://md.research.elamur.ai/free/en/authors/yafei-shi/), [Jiawei Chen](https://md.research.elamur.ai/free/en/authors/jiawei-chen/), [Yang Li](https://md.research.elamur.ai/free/en/authors/yang-li/), [Yaojie Lu](https://md.research.elamur.ai/free/en/authors/yaojie-lu/), [Hongyu Lin](https://md.research.elamur.ai/free/en/authors/hongyu-lin/), [Ben He](https://md.research.elamur.ai/free/en/authors/ben-he/), [Le Sun](https://md.research.elamur.ai/free/en/authors/le-sun/), [Bo Zheng](https://md.research.elamur.ai/free/en/authors/bo-zheng/) and [Xianpei Han](https://md.research.elamur.ai/free/en/authors/xianpei-han/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.eacl-long.384/) · [PDF](https://aclanthology.org/2026.eacl-long.384.pdf) · [DOI 10.18653/v1/2026.eacl-long.384](https://doi.org/10.18653/v1/2026.eacl-long.384) · [OpenAlex](https://openalex.org/W7140109045)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Web agents built on LLMs tend to commit to whatever step looks best at the moment. Once they take a wrong turn on a constantly changing website, they rarely retrace their steps. Tree-search alternatives can backtrack, but they are computationally heavy, struggle with irreversible web actions, and mostly depend on closed models such as GPT-4o.

The authors propose HintNavigator, a multi-agent framework inspired by the ACT-R theory of human cognition. It divides interaction history into two streams:
- **Declarative History:** facts gathered from page observations.
- **Procedural History:** previous actions and the reasoning behind them.

A dedicated agent processes each stream, and their outputs are merged into a working memory. From this memory, the system produces short textual "hints" that tell a policy agent when and where to return, for example with go back or goto actions. The authors call this strategy In-Context Exploration. The LLM itself stays fixed; nothing is fine-tuned.

On WebArena, HintNavigator reaches the best results reported among open-source LLM agents and outperforms Claude-3.5 Sonnet. This suggests that capable web agents need not rely on proprietary models.

## Key points
- **Backtracking gap:** Existing reactive agents (SteP, AgentOccam-J, the WebArena baseline) backtrack in at most about 16% of steps. Human browsing data puts the figure at roughly 30–50%.
- **Problem framing:** Navigation is modelled as a POMDP. Observations consist of the goal, the accessibility tree, and the URL.
- **Architecture:** Three agents collaborate: a Declarative Agent, a Procedural Agent that generates hints, and a Policy Agent.
- **Error analysis:** The authors manually examined 100 failed trajectories from Qwen-2.5 72B Instruct. They grouped the failures into four types: completion hallucination, information extraction failure, goal misunderstanding, and failure to recover.
- **Stated limitation:** Training on web navigation trajectories was not explored; the authors see it as a likely route to further gains.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 194 works · 23,906 citations
- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 147 works · 8,480 citations
- [Ant Group](https://md.research.elamur.ai/free/en/companies/ant-group/) — Company, Hangzhou, China · 42 works · 1,131 citations
- [Institute of Software](https://md.research.elamur.ai/free/en/labs/institute-of-software/) — Research institute, Beijing, China · 21 works · 4,980 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

## Cite

Cite as: Guozhao Mo, Yanjiang Liu, Yafei Shi, Jiawei Chen, Yang Li, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Bo Zheng and Xianpei Han. 2026. Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{mo2026navigating,
  title = {{Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration}},
  author = {Guozhao Mo, Yanjiang Liu, Yafei Shi, Jiawei Chen, Yang Li, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Bo Zheng and Xianpei Han},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.384},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.384}
}
```

- [← previous NASIMLab at SemEval-2026 Task 9: A Comparative Analysis of Fine-Tuned Small Language Models vs. Generative Large Language Models for Multilingual Polarization Type Detection](https://md.research.elamur.ai/free/en/papers/sabhahit-2026-nasimlab-semeval-2026-task-9/)
- [next → NE-LID: A Fast and Accurate Language Identification System for Northeast Indian Languages](https://md.research.elamur.ai/free/en/papers/nyalang-2026-ne-lid-fast-accurate-language/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/)

## References

40 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. John R. Anderson. 1983. The Architecture of Cognition. Harvard University Press. [find](https://scholar.google.com/scholar?q=John+R%2E+Anderson%2E+1983%2E+The+Architecture+of+Cognition%2E+Harvard+University+Press%2E)
2. John R Anderson. 1993. Problem solving and learning. American psychologist, 48(1):35. [find](https://scholar.google.com/scholar?q=John+R+Anderson%2E+1993%2E+Problem+solving+and+learning%2E+American+psychologist%2C+48%281%29%3A35%2E)
3. Anthropic. 2024a. Introducing claude 3.5 sonnet. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2024a%2E+Introducing+claude+3%2E5+sonnet%2E)
4. Cameron B. Browne, Edward Powley, Daniel Whitehouse, Simon M. Lucas, Peter I. Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez, Spyridon Samothrakis, and Simon Colton. 2012. A survey of monte carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in Games, 4(1):1… [find](https://scholar.google.com/scholar?q=Cameron+B%2E+Browne%2C+Edward+Powley%2C+Daniel+Whitehouse%2C+Simon+M%2E+Lucas%2C+Peter+I%2E+Cowling%2C+Philipp+Rohlfshagen%2C+Stephen+Tavener%2C+Diego+Perez%2C+Spyridon+Samothrakis%2C+and+Simon+Colton%2E+2012%2E+A+survey+of+mont)
5. Hyungjoo Chae, Namyoung Kim, Kai Tzu iunn Ong, Minju Gwak, Gwanwoo Song, Jihoon Kim, Sunghwan Kim, Dongha Lee, and Jinyoung Yeo. 2024. Web agents with world models: Learning and leveraging environment dynamics in web navigation. Preprint, arXiv:2410.13232. — [arXiv:2410.13232](https://arxiv.org/abs/2410.13232) [find](https://scholar.google.com/scholar?q=Hyungjoo+Chae%2C+Namyoung+Kim%2C+Kai+Tzu+iunn+Ong%2C+Minju+Gwak%2C+Gwanwoo+Song%2C+Jihoon+Kim%2C+Sunghwan+Kim%2C+Dongha+Lee%2C+and+Jinyoung+Yeo%2E+2024%2E+Web+agents+with+world+models%3A+Learning+and+leveraging+environment)
6. Thibault Le Sellier De Chezelles, Maxime Gasse, Alexandre Drouin, Massimo Caccia, Léo Boisvert, Megh Thakkar, Tom Marty, Rim Assouel, Sahar Omidi Shayegan, Lawrence Keunho Jang, Xing Han Lù, Ori Yoran, Dehan Kong, Frank F. Xu, Siva Reddy, Quentin Cappart, Graham Neubig, Ruslan Salakhutdinov, Nicolas… [find](https://scholar.google.com/scholar?q=Thibault+Le+Sellier+De+Chezelles%2C+Maxime+Gasse%2C+Alexandre+Drouin%2C+Massimo+Caccia%2C+L%C3%A9o+Boisvert%2C+Megh+Thakkar%2C+Tom+Marty%2C+Rim+Assouel%2C+Sahar+Omidi+Shayegan%2C+Lawrence+Keunho+Jang%2C+Xing+Han+L%C3%B9%2C+Ori+Yoran)
7. ANDY COCKBURN and BRUCE MCKENZIE. 2001. What do web users do? an empirical analysis of web use. International Journal of Human-Computer Studies, 54(6):903–922. [find](https://scholar.google.com/scholar?q=ANDY+COCKBURN+and+BRUCE+MCKENZIE%2E+2001%2E+What+do+web+users+do%3F+an+empirical+analysis+of+web+use%2E+International+Journal+of+Human%2DComputer+Studies%2C+54%286%29%3A903%E2%80%93922%2E)
8. Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. [Mind2web: Towards a generalist agent for the web](https://md.research.elamur.ai/free/en/papers/deng-2023-mind2web-towards-generalist-agent-web/). In Advances in Neural Information Processing Systems, volume 36, pages 28091–28114. Curran Associates, Inc.
9. Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, David Vazquez, Nicolas Chapados, and Alexandre Lacoste. 2024. WorkArena: How capable are web agents at solving common knowledge work tasks? In Proceedings of the 41st International Conference on Machine Le… [find](https://scholar.google.com/scholar?q=Alexandre+Drouin%2C+Maxime+Gasse%2C+Massimo+Caccia%2C+Issam+H%2E+Laradji%2C+Manuel+Del+Verme%2C+Tom+Marty%2C+David+Vazquez%2C+Nicolas+Chapados%2C+and+Alexandre+Lacoste%2E+2024%2E+WorkArena%3A+How+capable+are+web+agents+at+so)
10. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
11. Yu Gu, Boyuan Zheng, Boyu Gou, Kai Zhang, Cheng Chang, Sanjari Srivastava, Yanan Xie, Peng Qi, Huan Sun, and Yu Su. 2024. Is your llm secretly a world model of the internet? model-based planning for web agents. Preprint, arXiv:2411.06559. — [arXiv:2411.06559](https://arxiv.org/abs/2411.06559) [find](https://scholar.google.com/scholar?q=Yu+Gu%2C+Boyuan+Zheng%2C+Boyu+Gou%2C+Kai+Zhang%2C+Cheng+Chang%2C+Sanjari+Srivastava%2C+Yanan+Xie%2C+Peng+Qi%2C+Huan+Sun%2C+and+Yu+Su%2E+2024%2E+Is+your+llm+secretly+a+world+model+of+the+internet%3F+model%2Dbased+planning+for+w)
12. Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, and Dong Yu. 2024. [WebVoyager: Building an end-to-end web agent with large multimodal models](https://md.research.elamur.ai/free/en/papers/he-2024-webvoyager-building-end-end-web/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p…
13. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/).
14. Philipp Koehn. 2004. [Statistical significance tests for machine translation evaluation](https://md.research.elamur.ai/free/en/papers/koehn-2004-statistical-significance-tests-machine-translation/). In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pages 388– 395, Barcelona, Spain. Association for Computational Linguistics.
15. Jing Yu Koh, Stephen McAleer, Daniel Fried, and Ruslan Salakhutdinov. 2024. Tree search for language model agents. Preprint, arXiv:2407.01476. [find](https://scholar.google.com/scholar?q=Jing+Yu+Koh%2C+Stephen+McAleer%2C+Daniel+Fried%2C+and+Ruslan+Salakhutdinov%2E+2024%2E+Tree+search+for+language+model+agents%2E+Preprint%2C+arXiv%3A2407%2E01476%2E)
16. Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, and Jie Tang. 2024. [Autowebglm: A large language model-based web navigating agent](https://md.research.elamur.ai/free/en/papers/lai-2024-autowebglm-large-language-model-based/). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, K…
17. Evan Zheran Liu, Kelvin Guu, Panupong Pasupat, and Percy Liang. 2018. Reinforcement learning on web interfaces using workflow-guided exploration. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Evan+Zheran+Liu%2C+Kelvin+Guu%2C+Panupong+Pasupat%2C+and+Percy+Liang%2E+2018%2E+Reinforcement+learning+on+web+interfaces+using+workflow%2Dguided+exploration%2E+In+International+Conference+on+Learning+Representation)
18. Yanjiang Liu, Tianyun Zhong, Yaojie Lu, Hongyu Lin, Ben He, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, and Le Sun. 2024. XMC-agent : Dynamic navigation over scalable hierarchical index for incremental extreme multi-label classification. In Findings of the Association for Comp… [find](https://scholar.google.com/scholar?q=Yanjiang+Liu%2C+Tianyun+Zhong%2C+Yaojie+Lu%2C+Hongyu+Lin%2C+Ben+He%2C+Shuheng+Zhou%2C+Huijia+Zhu%2C+Weiqiang+Wang%2C+Zhongyi+Liu%2C+Xianpei+Han%2C+and+Le+Sun%2E+2024%2E+XMC%2Dagent+%3A+Dynamic+navigation+over+scalable+hierarchic)
19. Jiayi Pan, Yichi Zhang, Nicholas Tomlin, Yifei Zhou, Sergey Levine, and Alane Suhr. 2024a. Autonomous evaluation and refinement of digital agents. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Jiayi+Pan%2C+Yichi+Zhang%2C+Nicholas+Tomlin%2C+Yifei+Zhou%2C+Sergey+Levine%2C+and+Alane+Suhr%2E+2024a%2E+Autonomous+evaluation+and+refinement+of+digital+agents%2E+In+First+Conference+on+Language+Modeling%2E)
20. Yichen Pan, Dehan Kong, Sida Zhou, Cheng Cui, Yifei Leng, Bing Jiang, Hangyu Liu, Yanyi Shang, Shuyan Zhou, Tongshuang Wu, and Zhengyang Wu. 2024b. Webcanvas: Benchmarking web agents in online environments. Preprint, arXiv:2406.12373. — [arXiv:2406.12373](https://arxiv.org/abs/2406.12373) [find](https://scholar.google.com/scholar?q=Yichen+Pan%2C+Dehan+Kong%2C+Sida+Zhou%2C+Cheng+Cui%2C+Yifei+Leng%2C+Bing+Jiang%2C+Hangyu+Liu%2C+Yanyi+Shang%2C+Shuyan+Zhou%2C+Tongshuang+Wu%2C+and+Zhengyang+Wu%2E+2024b%2E+Webcanvas%3A+Benchmarking+web+agents+in+online+environ)
21. Zehan Qi, Xiao Liu, Iat Long Iong, Hanyu Lai, Xueqiao Sun, Wenyi Zhao, Yu Yang, Xinyue Yang, Jiadai Sun, Shuntian Yao, Tianjie Zhang, Wei Xu, Jie Tang, and Yuxiao Dong. 2025. Webrl: Training llm web agents via self-evolving online curriculum reinforcement learning. Preprint, arXiv:2411.02337. — [arXiv:2411.02337](https://arxiv.org/abs/2411.02337) [find](https://scholar.google.com/scholar?q=Zehan+Qi%2C+Xiao+Liu%2C+Iat+Long+Iong%2C+Hanyu+Lai%2C+Xueqiao+Sun%2C+Wenyi+Zhao%2C+Yu+Yang%2C+Xinyue+Yang%2C+Jiadai+Sun%2C+Shuntian+Yao%2C+Tianjie+Zhang%2C+Wei+Xu%2C+Jie+Tang%2C+and+Yuxiao+Dong%2E+2025%2E+Webrl%3A+Training+llm+web+a)
22. Qwen, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xu… [find](https://scholar.google.com/scholar?q=Qwen%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+Yan)
23. Tianlin Shi, Andrej Karpathy, Linxi Fan, Jonathan Hernandez, and Percy Liang. 2017. World of bits: An open-domain platform for web-based agents. In Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 3135–3144. PMLR. [find](https://scholar.google.com/scholar?q=Tianlin+Shi%2C+Andrej+Karpathy%2C+Linxi+Fan%2C+Jonathan+Hernandez%2C+and+Percy+Liang%2E+2017%2E+World+of+bits%3A+An+open%2Ddomain+platform+for+web%2Dbased+agents%2E+In+Proceedings+of+the+34th+International+Conference+on+)
24. David Silver and Joel Veness. 2010. Monte-carlo planning in large pomdps. In Advances in Neural Information Processing Systems, volume 23. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=David+Silver+and+Joel+Veness%2E+2010%2E+Monte%2Dcarlo+planning+in+large+pomdps%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+23%2E+Curran+Associates%2C+Inc%2E)
25. Paloma Sodhi, S.R.K Branavan, Yoav Artzi, and Ryan McDonald. 2024. Step: Stacked LLM policies for web actions. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Paloma+Sodhi%2C+S%2ER%2EK+Branavan%2C+Yoav+Artzi%2C+and+Ryan+McDonald%2E+2024%2E+Step%3A+Stacked+LLM+policies+for+web+actions%2E+In+First+Conference+on+Language+Modeling%2E)
26. Hongjin Su, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Tao Yu, and Sercan Ö. Ark. 2025. Learn-by-interact: A data-centric framework for self-adaptive agents in realistic environments. Preprint, arXiv:2501.10893. — [arXiv:2501.10893](https://arxiv.org/abs/2501.10893) [find](https://scholar.google.com/scholar?q=Hongjin+Su%2C+Ruoxi+Sun%2C+Jinsung+Yoon%2C+Pengcheng+Yin%2C+Tao+Yu%2C+and+Sercan+%C3%96%2E+Ark%2E+2025%2E+Learn%2Dby%2Dinteract%3A+A+data%2Dcentric+framework+for+self%2Dadaptive+agents+in+realistic+environments%2E+Preprint%2C+arXiv%3A250)
27. Browser Use Team. 2024. Browser use. [https://github.com/browser-use/browser-use](https://github.com/browser-use/browser-use). 2025-10-05. [↗](https://github.com/browser-use/browser-use)
28. Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, and Subbarao Kambhampati. 2023. On the planning abilities of large language models - a critical investigation. In Advances in Neural Information Processing Systems, volume 36, pages 75993– 76005. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Karthik+Valmeekam%2C+Matthew+Marquez%2C+Sarath+Sreedharan%2C+and+Subbarao+Kambhampati%2E+2023%2E+On+the+planning+abilities+of+large+language+models+%2D+a+critical+investigation%2E+In+Advances+in+Neural+Information+)
29. Junyang Wang, Haiyang Xu, Haitao Jia, Xi Zhang, Ming Yan, Weizhou Shen, Ji Zhang, Fei Huang, and Jitao Sang. 2024a. Mobile-agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration. In Advances in Neural Information Processing Systems, volume 37, pages 2686–… [find](https://scholar.google.com/scholar?q=Junyang+Wang%2C+Haiyang+Xu%2C+Haitao+Jia%2C+Xi+Zhang%2C+Ming+Yan%2C+Weizhou+Shen%2C+Ji+Zhang%2C+Fei+Huang%2C+and+Jitao+Sang%2E+2024a%2E+Mobile%2Dagent%2Dv2%3A+Mobile+device+operation+assistant+with+effective+navigation+via+mul)
30. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al. 2024b. [A survey on large language model based autonomous agents](https://md.research.elamur.ai/free/en/papers/wang-2023-survey-large-language-model-based/). Frontiers of Computer Science, 18(6):186345.
31. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2024c. [Agent workflow memory](https://md.research.elamur.ai/free/en/papers/wang-2024-agent-workflow-memory/). Preprint, arXiv:2409.07429.
32. Ryen W. White and Steven M. Drucker. 2007. Investigating behavioral variability in web search. In Proceedings of the 16th International Conference on World Wide Web, WWW ’07, page 2130, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Ryen+W%2E+White+and+Steven+M%2E+Drucker%2E+2007%2E+Investigating+behavioral+variability+in+web+search%2E+In+Proceedings+of+the+16th+International+Conference+on+World+Wide+Web%2C+WWW+%E2%80%9907%2C+page+2130%2C+New+York%2C+NY%2C+)
33. Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, Dawn Song, Huan Sun, and Yu Su. 2025. An illusion of progress? assessing the current state of web agents. Preprint, arXiv:2504.01382. [find](https://scholar.google.com/scholar?q=Tianci+Xue%2C+Weijian+Qi%2C+Tianneng+Shi%2C+Chan+Hee+Song%2C+Boyu+Gou%2C+Dawn+Song%2C+Huan+Sun%2C+and+Yu+Su%2E+2025%2E+An+illusion+of+progress%3F+assessing+the+current+state+of+web+agents%2E+Preprint%2C+arXiv%3A2504%2E01382%2E)
34. A Action Space To ensure the agent’s ability to comprehensively execute all possible actions on a web page while minimizing the action space, we have carefully optimized our action space. The detailed action space is presented in Table 6. [find](https://scholar.google.com/scholar?q=A+Action+Space+To+ensure+the+agent%E2%80%99s+ability+to+comprehensively+execute+all+possible+actions+on+a+web+page+while+minimizing+the+action+space%2C+we+have+carefully+optimized+our+action+space%2E+The+detailed)
35. Ke Yang, Yao Liu, Sapana Chaudhary, Rasool Fakoor, Pratik Chaudhari, George Karypis, and Huzefa Rangwala. 2025. Agentoccam: A simple yet strong baseline for LLM-based web agents. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ke+Yang%2C+Yao+Liu%2C+Sapana+Chaudhary%2C+Rasool+Fakoor%2C+Pratik+Chaudhari%2C+George+Karypis%2C+and+Huzefa+Rangwala%2E+2025%2E+Agentoccam%3A+A+simple+yet+strong+baseline+for+LLM%2Dbased+web+agents%2E+In+The+Thirteenth+Int)
36. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In The Eleventh International Conference on Learning Representations.
37. Ilker Yengin and Ibrahim Furkan Ince. 2014. Applying the adaptive control of thought-rational theory into the design of mobile worked examples applications. International Journal of Robots, Education and Art, 4(2):21. [find](https://scholar.google.com/scholar?q=Ilker+Yengin+and+Ibrahim+Furkan+Ince%2E+2014%2E+Applying+the+adaptive+control+of+thought%2Drational+theory+into+the+design+of+mobile+worked+examples+applications%2E+International+Journal+of+Robots%2C+Education+)
38. Yao Zhang, Zijian Ma, Yunpu Ma, Zhen Han, Yu Wu, and Volker Tresp. 2025. Webpilot: A versatile and autonomous multi-agent system for web task execution with strategic exploration. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22):23378–23386. [find](https://scholar.google.com/scholar?q=Yao+Zhang%2C+Zijian+Ma%2C+Yunpu+Ma%2C+Zhen+Han%2C+Yu+Wu%2C+and+Volker+Tresp%2E+2025%2E+Webpilot%3A+A+versatile+and+autonomous+multi%2Dagent+system+for+web+task+execution+with+strategic+exploration%2E+Proceedings+of+the+A)
39. Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig. 2024. [Webarena: A realistic web environment for building autonomous agents](https://md.research.elamur.ai/free/en/papers/zhou-2023-webarena-realistic-web-environment-building/). In The Twelfth International Conference on Learning Representation…
40. Action Description wait [time] click [id] fill [id] [content] goto [url] go back send msg to user Wait time Click an element Fill an element Goto URL Go back of the page Send message to user *Table 6: Action space for agent to interact with web.* [find](https://scholar.google.com/scholar?q=Action+Description+wait+%5Btime%5D+click+%5Bid%5D+fill+%5Bid%5D+%5Bcontent%5D+goto+%5Burl%5D+go+back+send+msg+to+user+Wait+time+Click+an+element+Fill+an+element+Goto+URL+Go+back+of+the+page+Send+message+to+user+%2ATable+6%3A)

*Updated 1 November 2026*